Oddity's blogs

Het Alziende Algoritme: Privacy en Bias in Computer Vision

Gepost op Dec 9, 2023

In onze hedendaagse maatschappij ontstijgt het aantal bewakingscamera's het aantal patrouillerende politieagenten. Naarmate het gebruik van kunstmatige intelligentie (AI) op bewakingscamera's toeneemt, wordt de rol ervan in de openbare veiligheid steeds belangrijker. Oddity's missie is het gebruik van computer vision als een kracht voor het goede, met als doel de publieke veiligheid te verhogen zonder privacy daarvoor op te moeten offeren.

The Best Bang for Your Buck Hardware for Deep Learning (Updated 2023)

Geüpdate op Mar 27, 2023

Even though graphics processors were initially intended for gaming, computer science enthusiasts are well aware that they hold significant value in numerous other areas as well. With the supply chain problems gradually being resolved and prices becoming more stable, many individuals are keen to get their hands on the latest NVIDIA GPUs. This blog post is here to help you make an informed decision when selecting the ideal GPU for your deep learning projects!

Open Sourcing our RTSP Server and video-rs

Gepost op Sep 15, 2022

We are proud to announce that we have decided to open source two formerly internal Oddity projects that help us read, process and distribute video streams. First, we're open sourcing a Rust library called video-rs that can read, write, encode and decode video. Second, we're open sourcing our own custom RTSP server.

Detecting Seizures in Infants using Computer Vision

Gepost op Mar 3, 2021

Oddity’s aim is to shape the future of safety. Apart from our usual projects in the domain of public safety, such as in cities, we are also working on different ideas. Our intern Wikke, together with the University of Utrecht, is working on a detecting seizures in newborns.

Solving AI's Data Problem

Gepost op Mar 23, 2020

This blogpost offers a quick and approachable look at one of the technical deep learning problems faced at Oddity.ai and outlines how we go about solving such problems. In any deep learning application, the amount of data is an important factor for success. Gathering this data is not always an easy task. We are looking at alternative methods for increasing the size of our datasets, such as data synthesis.

The Stratumseind Pilot

Gepost op Jan 13, 2020

It has been six months since the start of our first pilot in Stratumseind, Eindhoven. Hence it’s time to write about our expectations, experiences, results, and outlooks. We’ve performed this pilot in collaboration with Axis Communications and the municipality of Eindhoven. This blogpost briefly discusses the results from this pilot and lays out our plan for the future.

Ethics of AI for Video Surveillance

Gepost op Dec 2, 2019

The path towards the successful application of artificial intelligence in video surveillance that we are taking as a society crosses a lot of junctions and making a wrong choice along the way can cause a very undesirable outcome. The promise of AI is immense but the risks are large too. It is of utmost importance that we are aware of this, that we keep thinking critically and that we enable an open and inclusive dialogue.

The Base Rate Fallacy

Gepost op Nov 25, 2019

When talking about Oddity’s violence recognition system, we are often asked what the accuracy of our algorithm is. This seems like an easy enough question, but while answering it, we quickly run into trouble. To explain why, we need to look into a concept known within statistics as the Base Rate Fallacy. In general, the Base Rate Fallacy concerns a psychological effect that clouds peoples’ judgement when presented with certain statistics.

The Startup Toolkit

Gepost op Jul 15, 2019

In my previous article I explained the importance of finding the problem-solution fit, and showed some parts of our go-to-market (GTM) approach. A multiple-case study with 12 founders of software startups located in The Netherlands, taught us that some aspects of the GTM approach are of significant value. We explain these industry lessons in this chapter, for which we coined the term The Startup Toolkit. The toolkit explains the six most important elements a startup should take into account to achieve the problem-solution fit and product-market fit.

Achieving Problem-Solution Fit for Startups

Gepost op Jun 23, 2019

Software startups around the world are struggling to survive. Usually, within two years from the startups’ creation, it is not competition but rather self-destruction that drives the majority of startups into failure. My previous post presented a go-to-market approach based on The Lean Startup, Design Thinking, The Lean Product Playbook, and The Startup Owner’s Manual, to provide structured guidance to startups. These strategies are all user-driven innovation strategies: they involve potential users, customers, or other stakeholders into the development process, thus maintaining a user-centred approach.